© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44090
    Prev
    Next
    INDEX
    Explanations

    z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     v
    -0.84
     z
    -0.71
     ratio
    -0.64
     h
    -0.63
     k
    -0.47
    ratio
    -0.46
     V
    -0.43
     x
    -0.43
     char
    -0.43
     har
    -0.42
    POSITIVE LOGITS
    rungsseite
    1.09
     Jefus
    0.98
     Majefty
    0.98
     متعلقه
    0.94
     myſelf
    0.94
     purpoſe
    0.93
     Anſ
    0.90
    InjectAttribute
    0.89
     himſelf
    0.89
     themſelves
    0.88
    Activations Density 0.771%

    No Known Activations